{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MHXCB3HKJLB52B4RPV63IPZ425","short_pith_number":"pith:MHXCB3HK","canonical_record":{"source":{"id":"2411.06176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"595ac568dfec5393f2023a857a674feac4230c3d6dbea4b1db8a69b2f1083608","abstract_canon_sha256":"be309505cec26675851e3448b7661c1d4bf0b6b8ad579ab222b1eecb06231c05"},"schema_version":"1.0"},"canonical_sha256":"61ee20ecea4ac3dd07917d7db43f3cd76c8dd565706d26867e5094e79ad6493e","source":{"kind":"arxiv","id":"2411.06176","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06176","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06176v1","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06176","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"pith_short_12","alias_value":"MHXCB3HKJLB5","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"pith_short_16","alias_value":"MHXCB3HKJLB52B4R","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"pith_short_8","alias_value":"MHXCB3HK","created_at":"2026-07-05T09:33:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MHXCB3HKJLB52B4RPV63IPZ425","target":"record","payload":{"canonical_record":{"source":{"id":"2411.06176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"595ac568dfec5393f2023a857a674feac4230c3d6dbea4b1db8a69b2f1083608","abstract_canon_sha256":"be309505cec26675851e3448b7661c1d4bf0b6b8ad579ab222b1eecb06231c05"},"schema_version":"1.0"},"canonical_sha256":"61ee20ecea4ac3dd07917d7db43f3cd76c8dd565706d26867e5094e79ad6493e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:42.517297Z","signature_b64":"EbfTS1WlEhgnfFE/5whzIqo3RCeHfEVh94VRrtWcDwgHRmoqxLmDvs99r6mLhTyDotJN11K5n/v1tl6fc2IuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61ee20ecea4ac3dd07917d7db43f3cd76c8dd565706d26867e5094e79ad6493e","last_reissued_at":"2026-07-05T09:33:42.516790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:42.516790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.06176","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:33:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLdeVtVppEMuMWsB0pqIYGyF7drhk6vC2bvBn3lp4T0Zp103V8joWOsR6Ws6lilEcdohSpPBnYt72slfcJ42Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:31:22.604770Z"},"content_sha256":"8f68e212b11a88a3f9a56664946507a4c1a798a900fc03841845ef3591eda703","schema_version":"1.0","event_id":"sha256:8f68e212b11a88a3f9a56664946507a4c1a798a900fc03841845ef3591eda703"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MHXCB3HKJLB52B4RPV63IPZ425","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaoqun Liu, Hou Pong Chan, Lidong Bing, Liying Cheng, Maojia Song, Sharifah Mahani Aljunied, Soujanya Poria, Yew Ken Chia","submitted_at":"2024-11-09T13:30:38Z","abstract_excerpt":"The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are very time-consuming for humans to read thoroughly. Hence, there is an urgent need to develop effective and automated methods to aid humans in this task. In this work, we introduce M-LongDoc, a benchmark of 851 samples, and an automated framework to evaluate the performance of large multimodal models. We further propose a retrieval-aware tuning approach for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06176","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.06176/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:33:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3gLI6clipyAVZtAOhIhQiTL82kkt2UCn/F8+Qkl4O1+zvLou3d/sMjJuc+9l22tfB1mDvyoXRN02eaVyR5rAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:31:22.605135Z"},"content_sha256":"4fa7d015be37b661c5d0403c3a5fef63132427721f9449da84cd56534c95305d","schema_version":"1.0","event_id":"sha256:4fa7d015be37b661c5d0403c3a5fef63132427721f9449da84cd56534c95305d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/bundle.json","state_url":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MHXCB3HKJLB52B4RPV63IPZ425/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T19:31:22Z","links":{"resolver":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425","bundle":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/bundle.json","state":"https://pith.science/pith/MHXCB3HKJLB52B4RPV63IPZ425/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MHXCB3HKJLB52B4RPV63IPZ425/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MHXCB3HKJLB52B4RPV63IPZ425","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"be309505cec26675851e3448b7661c1d4bf0b6b8ad579ab222b1eecb06231c05","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:30:38Z","title_canon_sha256":"595ac568dfec5393f2023a857a674feac4230c3d6dbea4b1db8a69b2f1083608"},"schema_version":"1.0","source":{"id":"2411.06176","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06176","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06176v1","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06176","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"pith_short_12","alias_value":"MHXCB3HKJLB5","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"pith_short_16","alias_value":"MHXCB3HKJLB52B4R","created_at":"2026-07-05T09:33:42Z"},{"alias_kind":"pith_short_8","alias_value":"MHXCB3HK","created_at":"2026-07-05T09:33:42Z"}],"graph_snapshots":[{"event_id":"sha256:4fa7d015be37b661c5d0403c3a5fef63132427721f9449da84cd56534c95305d","target":"graph","created_at":"2026-07-05T09:33:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.06176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are very time-consuming for humans to read thoroughly. Hence, there is an urgent need to develop effective and automated methods to aid humans in this task. In this work, we introduce M-LongDoc, a benchmark of 851 samples, and an automated framework to evaluate the performance of large multimodal models. We further propose a retrieval-aware tuning approach for e","authors_text":"Chaoqun Liu, Hou Pong Chan, Lidong Bing, Liying Cheng, Maojia Song, Sharifah Mahani Aljunied, Soujanya Poria, Yew Ken Chia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:30:38Z","title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06176","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8f68e212b11a88a3f9a56664946507a4c1a798a900fc03841845ef3591eda703","target":"record","created_at":"2026-07-05T09:33:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"be309505cec26675851e3448b7661c1d4bf0b6b8ad579ab222b1eecb06231c05","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:30:38Z","title_canon_sha256":"595ac568dfec5393f2023a857a674feac4230c3d6dbea4b1db8a69b2f1083608"},"schema_version":"1.0","source":{"id":"2411.06176","kind":"arxiv","version":1}},"canonical_sha256":"61ee20ecea4ac3dd07917d7db43f3cd76c8dd565706d26867e5094e79ad6493e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61ee20ecea4ac3dd07917d7db43f3cd76c8dd565706d26867e5094e79ad6493e","first_computed_at":"2026-07-05T09:33:42.516790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:42.516790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EbfTS1WlEhgnfFE/5whzIqo3RCeHfEVh94VRrtWcDwgHRmoqxLmDvs99r6mLhTyDotJN11K5n/v1tl6fc2IuAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:42.517297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06176","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f68e212b11a88a3f9a56664946507a4c1a798a900fc03841845ef3591eda703","sha256:4fa7d015be37b661c5d0403c3a5fef63132427721f9449da84cd56534c95305d"],"state_sha256":"eed4c4448d33200cf154bf8887bb0406de7be5834f1f6ec081c801021f01320e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gkO2kVVzGS7t51Ffih+ZyNHtg8oeU/N73WOtIwbRs5jMJjtx4W9IY0Yu1RDk4bF512auR2nzWTiQeb/TZmSEBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:31:22.607071Z","bundle_sha256":"7b4cd22091f550da5250ec2be242985e823107335092758fbc585830bdf9d020"}}